Initial patch for OFED 1.5.x to work on RHEL 6
Hi all, Taking a look at the RHEL6 beta at the moment. It was failing compilation of OFED 1.5.1 release on the main ofa kernel rpm, giving the same error reported by Jeremy Enos back in Aug 2009 on Fedora 10. Thankfully the problem turned out to be a bug in the scripting in the rpm's spec file, easily fixed, which let's this now compile fine: ** --- ofa_kernel.spec_orig2010-04-28 13:01:43.505217495 +1000 +++ ofa_kernel.spec 2010-04-28 13:52:44.386217393 +1000 @@ -188,6 +188,7 @@ if [ -n $modsyms ]; then for modsym in $modsyms do + mkdir -p $RPM_BUILD_ROOT/%{_prefix}/src/%{_name} cat $modsym $RPM_BUILD_ROOT/%{_prefix}/src/%{_name}/Module.symvers done else @@ -800,9 +801,7 @@ %files -n kernel-ib-devel %defattr(-,root,root,-) %dir %{_prefix}/src -%{_prefix}/src/%{_name}-%{_version} %{_prefix}/src/%{_name} -%{_prefix}/src/openib %endif # END Files ** The mkdir -p is the important part that needed adding, and should be safe to add on all the platforms. Near the end however, it needed the removal of two directories not built on RHEL 6. Not sure if they do get built on other platforms though. Vladimir Sokolovsky would probably know. :) Hope that helps. Regards and best wishes, Justin Clift -- Salasaga - Open Source eLearning IDE http://www.salasaga.org -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: opensm with multiple IB subnets
We should really put this on the wiki. :) On 04/22/2010 12:56 AM, Yevgeny Kliteynik wrote: snip OpenSM dumps various files to /var/log and /var/cache/opensm folders. When you have more than one OpenSM process, they will all dump the same files, which is probably not a good idea. To change the output directories, set the OSM_TMP_DIR and OSM_CACHE_DIR env. variables to some other place. In addition, you need to make sure that each SM instance prints its log in a different place. You need to do something like this: foreach guid in guid_list export OSM_TMP_DIR=/tmp/osm_dump_dir${guid} export OSM_CACHE_DIR=/tmp/osm_dump_dir${guid} opensm --log_file /tmp/osm_dump_dir${guid}/osm.log -g ${guid} [your other options] -- Yevgeny snip -- Salasaga - Open Source eLearning IDE http://www.salasaga.org -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Weird board ID
Hi all, Just received an old Topspin 2 port PCIe card (MTLP25208-C), using firmware 4.6.0 and thought I'd update it to the latest firmware before trying to do anything with it. However, the board id is being reported really strangely: $ sudo mstflint -d mthca0 q Image type: Failsafe I.S. Version:1 Chip Revision: A0 Description: Node Port1Port2 Sys image GUIDs: 0005ad0467fc 0005ad0467fd 0005ad0467fe 0005ad0467ff Board ID:q�� VSD: q�� PSID: $ Does anyone know what that's about? Was considering the firmware on the board may be stuffed, but it seems to be verifying ok: $ sudo mstflint -d mthca0 v Failsafe image: Invariant /0x0028-0x095f (0x000938)/ (BOOT2) - OK Primary Image /0x0001-0x00010107 (0x000108)/ (Pointer Sector)- OK /0x00030028-0x000308af (0x000888)/ (BOOT2) - OK /0x000308b0-0x000348df (0x004030)/ (BOOT2) - OK /0x000348e0-0x00036bd3 (0x0022f4)/ (Configuration) - OK /0x00036bd4-0x00036c07 (0x34)/ (GUID) - OK /0x00036c08-0x0004452f (0x00d928)/ (DDR) - OK /0x00044530-0x0004c97b (0x00844c)/ (DDR) - OK /0x0004c97c-0x000617a3 (0x014e28)/ (DDR) - OK /0x000617a4-0x00074813 (0x013070)/ (DDR) - OK /0x00074814-0x00077883 (0x003070)/ (DDR) - OK /0x00077884-0x00078f37 (0x0016b4)/ (DDR) - OK /0x00078f38-0x00078f4b (0x14)/ (Configuration) - OK /0x00078f4c-0x00078f8f (0x44)/ (Jump addresses) - OK /0x00078f90-0x00082bf3 (0x009c64)/ (EMT Service) - OK Secondary Image /0x0002-0x00020107 (0x000108)/ (Pointer Sector)- OK /0x00090028-0x000908af (0x000888)/ (BOOT2) - OK /0x000908b0-0x000948df (0x004030)/ (BOOT2) - OK /0x000948e0-0x00096bd3 (0x0022f4)/ (Configuration) - OK /0x00096bd4-0x00096c07 (0x34)/ (GUID) - OK /0x00096c08-0x000a452f (0x00d928)/ (DDR) - OK /0x000a4530-0x000ac97b (0x00844c)/ (DDR) - OK /0x000ac97c-0x000c17a3 (0x014e28)/ (DDR) - OK /0x000c17a4-0x000d4813 (0x013070)/ (DDR) - OK /0x000d4814-0x000d7883 (0x003070)/ (DDR) - OK /0x000d7884-0x000d8f37 (0x0016b4)/ (DDR) - OK /0x000d8f38-0x000d8f4b (0x14)/ (Configuration) - OK /0x000d8f4c-0x000d8f8f (0x44)/ (Jump addresses) - OK /0x000d8f90-0x000e2bf3 (0x009c64)/ (EMT Service) - OK FW image verification succeeded. Image is bootable. $ * This is interesting too (hopefully the correct firmware image). Not that it's not extracting a correct firmware version number? $ sudo mstflint -d mthca0 -i fw-25208-4_8_200-MHEL-CF128-T.bin -nofs b Current FW version on flash: N/A New FW version: N/A Burn process will not be failsafe. No checks will be performed. ALL flash, including the Invariant Sector will be overwritten. If this process fails, computer may remain in an inoperable state. Do you want to continue ? (y/n) [n] : n $ -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Ok to edit the OpenFabrics wiki?
Hi all, Just went to update some of the info on the OpenFabrics wiki (ie motherboard compatibility), plus remove some of the spam in comments (ie. pr0n links). However, after registering and confirming email address, the wiki doesn't appear to be actually logging me in. New problem, or do I need to be manually added to an approved editor list or something? :) Regards and best wishes, Justin Clift -- Salasaga - Open Source eLearning IDE http://www.salasaga.org -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
NFS-RDMA on SLES 10 SP3
Hi all, After discovering that ofa kernel doesn't compile any more (with 1.5.1 GA and 1.5.2 latest nightly) on SLES 11 with the latest patches, now trying on SLES 10 SP3. I'm attempting to try out NFS-RDMA, however on SLES 10 SP3 it's not being presented as an option from the Custom list. i.e.: Install rds-tools? [y/N]:n Install rnfs-utils? [y/N]:y --- this line completely missing Install ibutils? [y/N]: ... Thought I'd better ask if this is expected behaviour before I file a bug report, as SLES10 SP3 is specifically mentioned in the NFS-RDMA release notes as being supported. ? (I've worked around the above problem by just changing the install.pl file. Compiles fine. But, thought it best to ask just in case.) Regards and best wishes, Justin Clift -- Salasaga - Open Source eLearning IDE http://www.salasaga.org -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: NFS-RDMA on SLES 10 SP3
Steve Wise wrote: OFED-1.5.1 removed support for NFS-RDMA on SLES 10 SP3 due to stability problems. No worries, thanks. :) Regards and best wishes, Justin Clift -- Salasaga - Open Source eLearning IDE http://www.salasaga.org -- To unsubscribe from this list: send the line unsubscribe linux-rdma in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html